Wan 2.7
Wan 2.7 is an image generation model from Wan, available via Wavespeed, priced at $0.03 per image.
Wan
WaveSpeedImage generation with source image support
Wan 2.7 is an image generation model published by Wan and served through the Wavespeed provider on MindStudio. Released in February 2026, it accepts source images as input alongside text prompts, enabling image-to-image workflows in addition to standard generation. The model supports configurable output dimensions through explicit width and height parameters, and includes a seed input for reproducible results.
Wan 2.7 is suited for workflows that require consistent, controllable image outputs, particularly when starting from a reference image. Its thinking mode selector adds an optional reasoning step to the generation process, which can influence how prompts are interpreted. At a flat rate of $0.03 per image, it is straightforward to budget for production use cases within MindStudio applications.
What Wan 2.7 supports
Source Image Input
Accepts one or more reference images as input, enabling image-to-image generation workflows rather than text-only prompting.
Custom Output Dimensions
Allows explicit numeric control over output width and height, giving developers precise control over image resolution and aspect ratio.
Reproducible Generation
Supports a seed parameter so the same prompt and settings can produce consistent, repeatable image outputs across runs.
Thinking Mode
Includes a selectable thinking mode that applies an optional reasoning step to prompt interpretation before image generation begins.
Generation Mode Toggle
Provides a toggle group input to switch between generation modes, allowing different output behaviors from a single model endpoint.
Ready to build with Wan 2.7?
Get Started FreeCommon questions about Wan 2.7
How much does it cost to generate an image with Wan 2.7?
Wan 2.7 is priced at $0.03 per image generated, making it straightforward to estimate costs for production workloads.
What is the context window for Wan 2.7?
Wan 2.7 has a context window of 2,000 tokens, which applies to the text prompt input used to guide image generation.
Can I use an existing image as input to Wan 2.7?
Yes. Wan 2.7 accepts an array of image URLs as input, supporting image-to-image generation workflows alongside text prompts.
Can I control the output image size?
Yes. The model exposes separate numeric width and height inputs, allowing you to specify exact pixel dimensions for the generated image.
When was Wan 2.7 released?
Wan 2.7 was released in February 2026 and became available on MindStudio in April 2026.
Parameters & options
Input images to edit (1-3). Reference them as "Figure 1", "Figure 2", etc. in the prompt.
When enabled, the model reasons about prompt intent before generating, improving composition and prompt adherence.
Explore similar models
WanWan 2.7 Pro
Wan 2.7 Pro is an image generation model from Wan, available via Alibaba, priced at $0.075 per image.
WanWan 2.7
Wan 2.7 is an image generation model from Alibaba's Wan that supports source image inputs and custom dimensions at $0.03 per image.
WanWan 2.7 Pro
Wan 2.7 Pro is an image generation model from Wan that supports source image input and configurable output dimensions.
X.aiGrok Imagine 2.0
Grok Imagine 2.0 is an image generation model from X.ai that accepts source images and supports configurable aspect ratio, resolution, and quality.
QwenQwen Image 3.0
ByteDanceSeedream 5.0 Pro
Seedream 5.0 Pro is an image generation model from ByteDance that supports source image input and flexible aspect ratio and resolution controls.
WanWan 2.6
Wan 2.6 is an image generation model from Wan that accepts source images and text prompts to produce new images at $0.03 per image.
Start building with Wan 2.7
No API keys required. Create AI-powered workflows with Wan 2.7 in minutes — free.